Abstract: A method and system for personalized avatar generation. The method includes receiving a text prompt and generating a first pose based on the text prompt using a first model. The method also includes re-targeting the first pose to a target avatar body. The method also includes identifying a predefined avatar configuration corresponding to a user based on a profile of the user. The method also includes converting the target avatar body by applying the predefined avatar configuration to the target avatar body. The method also includes rendering an avatar, using a second model, based on the target avatar body with the predefined avatar configuration, wherein the avatar is in the first pose.

Abstract: A method and system for text-to-video generation. The method includes receiving a text input, generating a representation frame based on the text input using a model trained on text-image pairs, generating a set of frames based on the representation frame and a first frame rate, interpolating the set of frames to a higher frame rate, generating a first video based on the interpolated set of frames, increasing a resolution of the first video based on a first and second super-resolution model, and generating an output video based on a result of the super-resolution models.

Abstract: Methods, systems, and storage media for generating audio data includes receiving a text input. The method also includes receiving a plurality of representative audio sources and encoding the plurality of representative audio sources into a plurality of audio tokens. The method includes encoding the text input into a plurality of text representations. The method comprises mapping each audio tokens of the plurality of audio tokens to a text representation of the plurality of text representations. The method also comprises determining a relationship score based on mapping each audio tokens to the text representation, wherein the relationship score identifies a distribution of audio tokens from the plurality of audio tokens. The method and systems can also comprise decoding the subgroup of audio tokens to yield a reconstructed audio source.

Abstract: In one embodiment, a method includes accessing first sets of tokens associated with a desired task and one or more modalities associated with a context of the desired task, determining a second set of tokens for each of the one or more modalities using a classifier network associated with the modality, generating a number of embedding vectors by mapping the first sets of tokens and the second set of tokens associated with each of the one or more modalities to an embedding space, and producing a sequence of words addressing the desired task by processing the number of embedding vectors with an encoder-decoder network.